query_adapter.py 文件源码

def train_feature_finder(self, training_db, clf):
        training_sentences = []
        c = 0
        training_classes = []
        self.class_names = []
        self.vectorizer = CountVectorizer(analyzer = "word",   \
                              tokenizer = None,    \
                              preprocessor = None, \
                              stop_words = None,   \
                              max_features = 500)
        for key, value in training_db.iteritems():
            training_sentences += value
            training_classes += [c for i in range(len(value))] 
            c+=1
            self.class_names.append(key)
        train_data_features = self.vectorizer.fit_transform(training_sentences)
        train_data_features = train_data_features.toarray()
        clf = clf.fit( train_data_features, training_classes)
        return clf